Questions tagged [experiment-design]

The design of experiments (DOE) is the study of how to structure an information-gathering exercise where variation is present. In statistics, controlled experiments are usually implied, meaning that study units are randomly assigned to conditions where levels of a variable have been independently manipulated (prototypically into treatment & control groups).

Filter by
Sorted by
Tagged with
0
votes
1answer
13 views

Split plot design with psudo replicates

I am working on a project and need to analyze data that I know is an example of a split plot design but I am having trouble setting the model up correctly. Here's the situation: A bakery is testing ...
2
votes
1answer
16 views

How to solve confounding issue in experimental design?

In an experimental design, how to solve confounding issues? Building a regression to control for confounding variables, is it one solution?
1
vote
0answers
15 views

What is the design of this experiment and how do i analyze it

I carried out an experiment in two locations. For the two locations, the experimental set up was 95 genotypes of a plant in 3 replicates. For each replicate, I had 3 blocks in which the genotypes were ...
0
votes
0answers
10 views

How is this form of experimental statistical design called in English?

In my textbook there is a statistical design called "Полностью случайные модели", that can be literally translated as "Completely random models". But I'm looking for existing terminology, so I could ...
0
votes
0answers
20 views

Choose factors that best represent the entire space

(I'm brand-new here. I have strong mathematical and computing backgrounds, but little knowledge of statistics. If this question belongs elsewhere, I would appreciate a pointer to where.) I believe ...
0
votes
0answers
10 views

What practical use cases are there for the static group comparison design?

As far as I understand, the only difference between "the static group comparison design" and "the posttest-only control group design" is that the latter has randomized controlled trial (RCT), in other ...
0
votes
0answers
15 views

Experimental design and regression analysis

In a randomized experimental design, the variables represent participants are no statistical difference between control and treatment groups. However, some of these variables show statistically ...
3
votes
2answers
48 views

Can a cross-sectional study use incident cases?

I am struggling with the epidemiological definition of my clinical study design. Looking at the literature I take it that case-control studies are retrospective (i.e. you must look back on the ...
0
votes
0answers
29 views

How to evaluate the quality of sensors? [closed]

I want to perform a study in the near future where it is about to investigate a gas sensor. This means, I want to check how the sensor detects certain amount of different gases (like ...
0
votes
1answer
16 views

How to conduct a test for independence in case of skewed classes (experiment design)?

The setting is as follows. We have a population of size $N$. Each subject has two properties $A$ and $B$, which can be either true or false. The question is: if for a random subject $A$ holds, is the ...
0
votes
0answers
17 views

Need help finding the number of participants for a statistical test for my research

I am currently in the process of validating my research's results with a user study where I plan to ask $n$ participants to partake in an experiment to rate my results. The experiment will look like ...
0
votes
0answers
9 views

Testing blocking effects

In the two-way layout model with k treatments and n blocks, the method to remove block effects for testing treatment effects can also be applied to remove treatment effects for testing block effects ...
0
votes
1answer
9 views

When reverse item loaded on one factor when they are not supposed to

I'm conducting a survey online and one of my measurement is 'Credibility' variable, which uses total of 9 variable (see image). These variables are supposed to fall into three dimensions, which are ...
1
vote
0answers
20 views

Experimental design to estimate the sample size

I've been newly introduced to Experimental Design and I am wondering about its possible connection with multivariate classification models. Is it possible to build a DoE able to predict which is the ...
0
votes
0answers
7 views

Which is suitable Experimental Design and behavioural Model for mixed variables both in input and output

I am trying to find the suitable design of experiment to collect data and fit appropriate model for prediction. Sample size would be around 100-200 ans total variables 40. Both input and output ...
0
votes
0answers
24 views

Sampling Design Problem

I am comparing two types of areas, Intact forests and small patchy forests within agricultural areas (fragments). I was supposed to conduct my sampling inside the Intact forest using the average of ...
3
votes
0answers
29 views

Treatment interference (causal analysis)

I am doing research on students and their perception of their grades. Specifically, I want to do an experiment where students either (a) see their actual grades in a course (as a percentage) - the ...
0
votes
0answers
29 views

Question on this study design

If I'm looking to run a randomized controlled experiment comparing: Group A) control Group B) treatment 1 Group C) treatment 2 Group D) a combination of treatments 1 and 2 1) Can I reduce ...
0
votes
0answers
7 views

Difference between RCBD and Nested Plot Design

RCBD design with replicates looks same as Nested Plot design. Conceptually, what is the difference other than considering the "block" in RCBD as another factor?
0
votes
0answers
29 views

Is this study design sufficient to make causal claims from a multiple logistic regression model?

I have been tasked with designing a study for our sales team to estimate how different factors impact the success of prospects converting to various stages of our sales pipeline. To provide some ...
0
votes
0answers
7 views

Experiment design: what's the difference between diff in diff and post-stratification?

what's the difference between diff in diff and post-stratification? When should we use diff in diff and when should we use post_stratification quasi experiment design?
0
votes
0answers
7 views

reporting the minimum detectable difference (MDE) used in an experiment

I wanted to check my thinking regarding the following: whether when reporting on the results on an experiment, it's relevant to report the MDE alongside the p-value, especially if the experiment was ...
1
vote
1answer
29 views

Unequal variance in randomized experiments to compare treatment with control?

Consider a randomized experiment to compare (one or more) treatment(s) with a control. Since groups are defined by random assignment, we should expect equal variances for a null-experiment (that is, ...
0
votes
0answers
7 views

Research participants maknig simultaneous choice: is it between or within subject design?

This question is about terminology. Assume the following scenario. A research participant is asked to choose one out of four options: products A and B in packagings X and Y. That is, the choice (...
73
votes
13answers
7k views

Famous statistical wins and horror stories for teaching purposes

I am designing a one year program in data analysis with a local community college. The program aims to prepare students to handle basic tasks in data analysis, visualization and summarization, ...
0
votes
0answers
26 views

Designing a trial where the null hypothesis should not be rejected

Background I'm currently designing a trail to compare the risk of radial artery occlusion between two medical treatments (standard of care versus new approach). When performing cardiac ...
0
votes
0answers
8 views

Pre-Post Analysis and Accounting for Task Difficulty

The study We have a real world pre-post design where some people were trained and others were not trained. The goal is to determine if the training worked and improved performance overall. The ...
0
votes
0answers
12 views

How many center points shall I add?

Given this design: ...
52
votes
11answers
5k views

Famous easy to understand examples of a confounding variable invalidating a study

Are there any well-known statistical studies that were originally published and thought to be valid, but later had to be thrown out due to a confounding variable that wasn't taken into account? I'm ...
1
vote
0answers
11 views

DoE with correlated runs. Possible solutions?

I would like to create an optimal experimatal design (DoE) for a machine which will be used to produce 20 results in batch mode to find the most important factors which do have an impact on certain ...
2
votes
1answer
72 views

Bayesian A/B test analysis for non-binary actions

When analyzing experiments with binary action (for example, will a user convert or not), then Beta-Binomial distribution is apt for that. For example, to model Click Through Rate (CTR): ...
1
vote
1answer
33 views

D-optimal DOE suggest repeated samples

I tried to generate a D optimal design but the design output sounds very weird to me. I have a (real) process and I`d like to explore 3 factors, but the process have a lot of constraints so I provide ...
1
vote
1answer
26 views

Advise for two non gaussian distribution group

I have a dataset which test the introduction of a new measure of a luggage checking a local small airport, the aim is to conclude whether the new measure reduce the luggage checking time. My dataset ...
0
votes
0answers
5 views

How do I appropriately take into account baseline item variance in a two-phase experimental design?

We are running a study with a two-phases experimental design: in the first phase, we ask subjects for intuitive scores about our items. In a second phase we ask people for an estimate that ...
1
vote
1answer
50 views

How to analyze experiment (based on DoE and via mixed model)?

I am about to deploy my DoE which is based on six parameters with two whole plots: Temperature and relative humidity. The experiment aims at studying a sensor due to the presence of several gases (...
1
vote
1answer
27 views

What if one experimental treatment affects whether another treatment is seen?

Suppose I run an experiment which tests which version of an email is most likely to cause people to click on a survey link inside the email. There are two experimental manipulations: the email ...
4
votes
1answer
52 views

Specifying mixed model in lmer for a single group reversal design

I have data on a simple experiment performed by one of my students looking at the effect of a single bout of aerobic exercise on working memory. The data are structured as follows: ...
0
votes
0answers
11 views

How to use mixed ANOVA with 2 between-subjects and 1 within-subjects design

I know mixed ANOVA should be used when testing a data set containing within-between subjects design. As my data structure shows below, my between-subjects factor is ...
2
votes
1answer
83 views

Standard errors of parameters in IRT

DeMars's Item Response Theory makes the following claims about parameter estimation in 3PL models: The standard error of $b$ (difficulty) will be smaller when there are more examinees with $\theta$ (...
0
votes
0answers
17 views

Between Subject Design with multiple Trials per participant

Between the subject experiment with two groups: Each group has a pair of 10 participants. (Player 1 and Player 2) Pairs in both groups play a game where one factor is manipulated. Hypothesis: The ...
0
votes
0answers
13 views

Minimum Detectable Effect (MDE) for churn rates

I am new to experimentation and could use some direction. The Minimum detectable effect (MDE) is a calculation that estimates the smallest improvement you’re willing to be able to detect in your ...
0
votes
0answers
8 views

What is a “regular” fractional factorial (2-level)?

What is the difference between a regular fractional factorial design and a non-regular fractional factorial design? I found it several times but especially in the FrF2-package.
0
votes
0answers
27 views

Optimal value for multiple input

I run an experiment in which every second I record values of area, circularity, and elongation (there will be probably more variables in the future). I want to find in which second there are the ...
0
votes
0answers
28 views

How to incorporate the customers leaving (addition of new ones) in the measurement of treatment effectiveness?

Consider I have taken a random sample for forming control group in month of January with sample size 5k and treatment group size being 95k. I am Sending offers to treatment group which are intend to ...
0
votes
0answers
20 views

Study Setup for a research project

I have 180 observations that were collected in a healthcare environment. The observations were identified in a prospective manner. Outcomes to be measured are accuracy of group A assessment when ...
0
votes
0answers
19 views

How to study split-plot design

Is it possible to study a split-plot design with a mixed model? I've seen a related question so I guess it is doable in general. Is there any certain function or procedure I can use? Or can you give ...
1
vote
0answers
39 views

Making one-sided conclusions from two-sided tests

I'm reading Montgomery's Design and Analysis of Experiments. On page 39, he rejected a two-sided $t$-test against the null hypothesis that modified formulation of some cement mortar doesn't change its ...
0
votes
1answer
25 views

How to study a fractional factorial design? [closed]

I wonder why a DoE/fractional factorial design isn't studied with the help of a linear mixed model? Or an Anova? How to analyze it in general is e.g. given here. Background: I will study several gas ...
1
vote
0answers
18 views

Repeated measures with sub-sample (and how to select them?)

We conducted an extensive survey on ethical behaviour in the workplace (N=5000). The results give an indication on different scales of the current state of the company. For example, one question is ...
1
vote
0answers
15 views

Interim analysis and alpha spending in group sequence design of clinical trials

In group sequential design, does the type of interim analysis affect the alpha spending for each look? I tested in ADDPLAN, with two interim analyses, specifying "stopping for futility" or not does ...